gws.mail.get_attachment

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behavioral traits beyond annotations: it returns base64-encoded bytes in the JSON payload (data_base64), includes filename, MIME type, and size, and wraps content in <untrusted-document-content> tags with a security warning about not following directives inside. This is critical behavioral context that annotations (readOnlyHint, openWorldHint) do not provide. The description adds significant value here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: it states the primary action in the first sentence, then provides necessary context about how to obtain the attachmentId, the return format, and a security warning. Every sentence earns its place, and the structure is logical. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 params, no output schema, no nested objects), the description is complete. It explains the return payload structure (filename, MIME type, size, data_base64), the security wrapper, and the source of attachmentId. The annotations cover read-only and non-destructive aspects, and the description covers the rest. No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds value by explaining the relationship between attachmentId and the read_message/read_thread tools, and clarifies the return format (data_base64). However, it doesn't add much beyond the schema for the 'account' parameter, which is already described. Baseline 3 plus the added context about attachmentId provenance and return format justifies a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a single attachment's bytes from a message, specifying the verb (fetch), resource (attachment), and scope (single attachment from a message). It also distinguishes itself from siblings by noting the attachmentId comes from mail.read_message / mail.read_thread, which is a clear differentiator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool: after obtaining attachmentId from mail.read_message or mail.read_thread. It also provides a clear exclusion: it fetches a single attachment, not multiple, and implies alternatives for listing messages. This is explicit usage guidance with a clear workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.